SA

Sakura13B LNovel v0.9b GGUF IMX 2.33 re

SakuraGGUF by shing3232Updated 2024-02-29
Download on Hugging Face
Parameters14.2B
Context8K
Layers40
Architectureqwen
Smallest quant6.6 GB
Quick answer

Sakura13B LNovel v0.9b GGUF IMX 2.33 re needs about 15.1 GB of memory at its main file (a 7.8 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 5 quants, from 6.6 GB to 10.0 GB.

Sakura13B LNovel v0.9b GGUF IMX 2.33 re is a 14.2B-parameter Sakura model in GGUF format, quantized by shing3232. Its trained context length is 8K tokens. The repository has 5 quant files, from 6.6 GB to 10.0 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—6.6 GB 13.8 GB
Too big Get file →
IQ4_XS7.8 GB 15.1 GB
Too big Get file →
—7.8 GB 15.1 GB
Too big Get file →
IQ4_NL8.2 GB 15.4 GB
Too big Get file →
—10.0 GB 17.2 GB
Too big Get file →

What GPU do you need for Sakura13B LNovel v0.9b GGUF IMX 2.33 re?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: the best quant that fits is IQ4_NL (8.2 GB file, about 15.4 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (10.0 GB file, about 17.2 GB in use).

Which Sakura13B LNovel v0.9b GGUF IMX 2.33 re quant should you choose?

If memory is tight, the smallest file is the first one in the table at 6.6 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen
Parameters14.2B
Layers40
Trained context8,192 tokens
KV cache (fp16)800 KB per token

Source

Quantized byshing3232
FamilySakura
Downloads (HF)52
Last updated2024-02-29

Frequently asked questions about Sakura13B LNovel v0.9b GGUF IMX 2.33 re

How much VRAM does Sakura13B LNovel v0.9b GGUF IMX 2.33 re need?

About 15.1 GB at its main file with an 8K context window. That is the 7.8 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Sakura13B LNovel v0.9b GGUF IMX 2.33 re on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 13.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Sakura13B LNovel v0.9b GGUF IMX 2.33 re GGUF?

It depends on the quant: file is 6.6 GB, IQ4_XS is 7.8 GB, file is 7.8 GB, IQ4_NL is 8.2 GB, file is 10.0 GB.

What context length does Sakura13B LNovel v0.9b GGUF IMX 2.33 re support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 6.7 GB at 8K and 6.7 GB at 8K.

Where can I download Sakura13B LNovel v0.9b GGUF IMX 2.33 re GGUF?

The files are on Hugging Face in the shing3232/Sakura13B-LNovel-v0.9b-GGUF-IMX-2.33_re repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from shing3232

All by shing3232 →

More Sakura models

All Sakura →

Other medium models

All medium models →